BAAI/bge-reranker-v2-m3

by BAAI

BAAI/bge-reranker-v2-m3 is a lightweight multilingual reranking model. It is developed based on the bge-m3 model, offering strong multilingual capabilities, easy deployment, and fast inference. The model takes a query and documents as input and directly outputs similarity scores instead of embedding vectors. It is suitable for multilingual scenarios and performs particularly well in both Chinese and English processing.

API Pricing

Input$0.03 / 1M tokens
Output$0.03 / 1M tokens

Specifications

Modalitiestext, image

Use BAAI/bge-reranker-v2-m3 via the AIHubMix unified API — one interface for every major LLM.